Multi- and hyperspectral remote sensing change detection with generalized difference images by the IR-MAD method

This contribution focuses on construction of more general difference images than simple differences in multivariate change detection. This is done via an iterated version of the canonical correlation analysis (CCA) based multivariate alteration detection (MAD) method combined with an EM-based method for determining thresholds for differentiating between change and no-change in the difference images, and for estimating the variance of the no-change observations. This variance is used to establish a single change/no-change image based on the general multivariate difference image. The resulting imagery from MAD based change detection are invariant to linear and affine transformations of the input including, e.g., affine corrections to normalize data between the two acquisition time points. This is an enormous advantage over other multivariate change detection methods. The resulting single change/no-change image can be used to establish both change regions and to extract observations based on which a fully automated orthogonal regression analysis based normalization of the multivariate data between the two points in time can be developed. Also, regularization issues typically important in connection with the analysis of hyperspectral data are dealt with.